Using Quick-Start to Improve TCP Performance with Vertical Hand-offs

Sarolahti, Pasi; Korhonen, Jouni; Daniel, Laila; Kojo, Markku

doi:10.1109/lcn.2006.322197

Cited by 14 publications

(17 citation statements)

References 16 publications

(20 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Section IV-B). In addition to avoiding initial Slow-Starts, the Quick-Start mechanism could also be quite useful in the middle of data transfers, e. g., after longer idle periods, or in combination with link layer mobility triggers [6]. QuickStart can thus complement other new high-speed congestion control mechanisms that target at environments with a large bandwidth-delay product (see e. g. [7]).…”

Section: B Benefits and Open Issues Of Quick-startmentioning

confidence: 99%

See 1 more Smart Citation

Performance analysis of the Quick-Start TCP extension

Scharf

2007

2007 Fourth International Conference on Broadband Communications, Networks and Systems (BROADNETS '07)

View full text Add to dashboard Cite

Abstract-Quick-Start is an experimental extension of the Transmission Control Protocol (TCP) that allows to speed up best effort data transfers. With Quick-Start, TCP hosts can request permission from the routers along a network path to send at a higher rate than allowed by the default TCP congestion control. The explicit router feedback avoids the time-consuming capacity probing by the TCP Slow-Start and is therefore particularly beneficial for underutilized paths with a high bandwidth-delay product. In this paper, the performance of the Quick-Start TCP extension is analyzed and the impact of router admission control strategies is studied. The main contribution is an analytical model that quantifies the improvement compared to default TCP Slow-Start. The model is validated by simulation results and by initial measurements with a Quick-Start implementation in the Linux operating system. Our results confirm that Quick-Start can significantly reduce the completion times of mid-sized data transfers. I. INTRODUCTIONThe Transmission Control Protocol (TCP) is the default transport protocol for best effort Internet services. Since TCP is a pure end-to-end protocol, the connection endpoints have to estimate the path characteristics in order to adapt their sending rate. However, after connection setup, or e. g. after long idle periods, it is difficult to determine an appropriate rate due to lack of information. Traditionally, the TCP congestion control uses the "Slow-Start" heuristic to probe the available bandwidth in these cases, but this is a time-consuming process, since it can require many round-trip times to reach an appropriate sending rate.The Quick-Start extension [1] addresses this issue by using explicit router feedback. It allows hosts to ask for an initial sending rate, e. g., during the TCP three-way handshake, and the routers along the path can approve, modify, or discard this request. If the Quick-Start request is approved, using a higher-than-default initial sending rate can significantly speed up high-speed best effort data transfers over paths with a large bandwidth-delay product, such as over long-distance broadband wide area networks, satellite or cellular links.Even though Quick-Start is only a minor extension of the TCP congestion control, its deployment has various implications on the architecture and performance of IP networks. An initial evaluation of Quick-Start in [2] quantifies the performance benefits compared to standard TCP and discusses basic router strategies. Yet, many details and trade-offs are not discussed in detail there, and the results are based on simulations only. This paper derives analytical approximations for

show abstract

Section: B Benefits and Open Issues Of Quick-startmentioning

confidence: 99%

“…It confirms significant benefits for the startup behavior of streaming traffic with "TCP Friendly Rate Control". Simulations in [6] show that Quick-Start can be used to improve the TCP performance after vertical handovers. The analytical analysis in the following section extends and complements this initial work on Quick-Start performance.…”

Section: Related Workmentioning

confidence: 99%

Performance analysis of the Quick-Start TCP extension

Scharf

2007

2007 Fourth International Conference on Broadband Communications, Networks and Systems (BROADNETS '07)

View full text Add to dashboard Cite

show abstract

“…Authors of [1]- [3] propose to hold the TCP sending during a handover and resume when the handover is finished. Freeze-TCP [1] resumes with the same window size, which is not appropriate for vertical handover, as we discussed before.…”

Section: Related Workmentioning

confidence: 99%

“…[2] solves this by letting TCP go through slow-start right after a handover. The idea is further developed in [3], where quickstart is used to negotiate the correct sending rate with traversing routers after the handover. For the problem of spurious retransmit timeout (RTO), [1], [2], [4] stop the retransmit timer or set it to a very large value during the handover, while [7], [8], [11] try to obtain the correct round-trip-time (RTT) estimation first and compute a new RTO based on it.…”

Section: Related Workmentioning

confidence: 99%

A fast adaptation mechanism for TCP vertical handover

Sleurs

Lil

et al. 2008

2008 International Conference on Advanced Technologies for Communications

View full text Add to dashboard Cite

Abstract-In this paper we propose a vertical handover mechanism for TCP to deal with the delay and bandwidth change during the handover. The proposed mechanism relies on the interaction between the sender and the receiver during the handover and requires no a prior information of the new path. The adaptation is triggered by a handover notification at the receiver and finishes in about two round-trip time. Furthermore, it solves the problem of packet reordering and spurious retransmission timeout as well which are also common during vertical handovers. Simulation results show that our mechanism improves TCP performance in various vertical handover scenarios.Index Terms-TCP, Handover, Congestion Control, Mobility.I. INTRODUCTION It is well-known that TCP does not perform well during a handover. A first reason is the possible packet loss during the outage time when the mobile node changes its network connection. Since TCP regards all packet loss as indication of congestion, it will back-off its sending rate unnecessarily. This problem can be readily solved in the network layer with lossless handover techniques such as buffer-and-forward and make-before-break. Unfortunately, this is not the end of problems. When the handover takes place between different type of networks, or in other words, when TCP experiences a vertical handover, the abrupt change in network delay and bandwidth will still affect its performance.When the new path has a higher bandwidth or a lower delay, packets following the new path may overtake those in the old one and arrive at the receiver earlier. Consecutive out-oforder packets can generate enough duplicate ACKs to trigger false fast retransmission while no packet is really lost. On the other hand, when the new path has a lower bandwidth or a higher delay, packets following the new path may not be acknowledged in time, which causes premature RTOs at the TCP sender. All these wrongly triggered congestion responses not only cause unnecessary packet retransmission but also greatly decrease the TCP throughput regardless of the real network conditions. Furthermore, since TCP does not control the sending rate directly but only the number of in-flight packets using a sliding-window based mechanism, it will try to keep the same amount of packets in the network also after a handover. If the Bandwidth-Delay Product (BDP) is changed during a handover -which is very likely the case for a vertical one -TCP will either overrun or under-utilize the capacity of the new path. Because the Additive-Increase MultiplicativeDecrease (AIMD) scheme used in TCP for window adjusting

show abstract

“…As there may be a significant change in link characteristics due to a vertical handoff, [8] studies the suitability of QuickStart [12] to set the cwnd and ssthresh after a vertical handoff. An explicit cross-layer handoff notification is employed to trigger Quick-Start when the handoff completes.…”

Section: Related Workmentioning

confidence: 99%

Using cross-layer information to improve TCP performance with vertical handoffs

Daniel

Kojo

2007

2007 Second International Conference on Access Networks &Amp; Workshops

Self Cite

View full text Add to dashboard Cite

In this paper we study the performance of TCP with a vertical handoff between access networks with widely varying link characteristics. TCP being an end-to-end protocol has performance problems as its behaviour depends on the endto-end path characteristics which are likely to be affected by a vertical handoff. We propose a set of enhancements to the TCP sender algorithm that leverage on explicit cross-layer information regarding the change in the access link delay and bandwidth. We apply our enhanced algorithms and carry out a systematic study comparing the performance of the regular TCP to the performance of the enhanced TCP algorithms in various handoff scenarios between access networks having widely different bandwidth and delay characteristics. Our experiments show that with cross-layer notifications TCP performance can be improved significantly in most vertical handoff scenarios.

show abstract

Using Quick-Start to Improve TCP Performance with Vertical Hand-offs

Cited by 14 publications

References 16 publications

Performance analysis of the Quick-Start TCP extension

Performance analysis of the Quick-Start TCP extension

A fast adaptation mechanism for TCP vertical handover

Using cross-layer information to improve TCP performance with vertical handoffs

Contact Info

Product

Resources

About